Skip to main content

Module gaussian_process

Module gaussian_process 

Source
Expand description

Gaussian Process regression (PRML ch 6.4) — a nonparametric Bayesian regressor that returns a full predictive distribution (mean, variance) at every input, with the squared-exponential (RBF) kernel. The training solve reuses linear_algebra::cholesky (no new solver). Kernel-class DenseLinear (the n×n kernel solve) + AllPairs (the kernel evaluations).

Given training (X, y) and noise variance σ²ₙ: mean(x*) = k*ᵀ (K + σ²ₙI)⁻¹ y, var(x*) = k(x*,x*) − k*ᵀ (K + σ²ₙI)⁻¹ k*, the calibrated uncertainty that collapses near training points and widens away from them.

Structs§

GpRegressor
A fitted GP regressor (squared-exponential kernel).